Skip to content

Free models · data of 2026-11-06

LFM2.5-2.6B: free API

LFM2.5-2.6B is free on OpenRouter as liquid/lfm-2.5-2.6b:free. Today it ranks #12 of 12 free chat models in our open ranking, with a score of 6/100.

Score basis
Published benchmarks
Served by
Liquid
Context
66K tokens
Max output
8K tokens
Input
text
Tool calling
Yes
JSON output
Yes
Free limit
20 RPM · 50 RPD

Does it train on your prompts?

The free variant is served only by Liquid that may train on your prompts. Don't send anything you would not want used for training.

From OpenRouter's published provider policies, checked 2026-10-22.

How good is it?

Coding index
7.7
Parameters
2.7B

The indexes are Artificial Analysis benchmarks as published by OpenRouter. How they combine into the score is in the ranking's scoring code.

How to call it

Any OpenAI-compatible client works. Create a key at openrouter.ai and use the model id above; the free limit is shared by all free models on your account.

from openai import OpenAI

client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key="sk-or-...")
reply = client.chat.completions.create(
    model="liquid/lfm-2.5-2.6b:free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Hit a limit? free-models-per-day, Provider returned error and other errors, explained. Limits and fine print: OpenRouter free models.

Questions

Is LFM2.5-2.6B free to use?
Yes, as liquid/lfm-2.5-2.6b:free on OpenRouter. Free models share one allowance per account: 20 RPM · 50 RPD, or 1,000 a day once the account has bought 10 credits.
Does LFM2.5-2.6B train on my prompts?
The free variant is served only by Liquid that may train on your prompts. Don't send anything you would not want used for training.
What is LFM2.5-2.6B's context window?
66K tokens of context, with up to 8K tokens of output.
How good is LFM2.5-2.6B compared with other free models?
It ranks #12 of 12 free chat models today with a score of 6/100 (basis: Published benchmarks).

Ranked next to it

Sources

Data of 2026-11-06, refreshed daily. Free models come and go: when this one leaves the free catalogue, this page goes with it.

Don't want to pick one model and handle its errors? ZeroLimitAI is one OpenAI-compatible endpoint that sends each request to the best free model available, and can run on your own Groq or OpenRouter key.

Stop paying per token.

One endpoint. $0 inference.

Free 7-day API key in a minute · no card. Then $99 once on your own key, or $99 a year.